In recent years, GPU-CPU heterogeneous architectures have been increasingly adopted in high performance computing, because of their capabilities of providing high computational throughput. However, the energy consumption is a major concern due to the large scale of such kind of systems. There are a few existing efforts that try to lower the energy consumption of GPU-CPU architectures, but they address either GPU or CPU in an isolated manner and thus cannot achieve maximized energy savings. In this paper, we propose Green GPU, a holistic energy management framework for GPU-CPU heterogeneous architectures. Our solution features a two-tier design. In the first tier, Green GPU dynamically splits and distributes workloads to GPU and CPU based on the workload characteristics, such that both sides can finish approximately at the same time. As a result, the energy wasted on idling and waiting for the slower side to finish is minimized. In the second tier, Green GPU dynamically throttles the frequencies of GPU cores and memory in a coordinated manner, based on their utilizations, for maximized energy savings with only marginal performance degradation. Likewise, the frequency and voltage of the CPU are scaled similarly. We implement Green GPU using the CUDA framework on a real physical test bed with Nvidia GeForce GPUs and AMD Phenom II CPUs. Experiment results show that Green GPU achieves 21.04% average energy savings and outperforms several well-designed baselines.
展开▼
机译：近年来，GPU-CPU异构体系结构由于其提供高计算吞吐量的能力而越来越多地用于高性能计算中。然而，由于这种系统的大规模，能量消耗是主要关注的问题。现有的一些努力试图降低GPU-CPU架构的能耗，但是它们以孤立的方式处理GPU或CPU，因此无法实现最大程度的节能。在本文中，我们提出了绿色GPU，这是一种用于GPU-CPU异构体系结构的整体能源管理框架。我们的解决方案具有两层设计。在第一层中，绿色GPU根据工作负载特征动态地将工作负载拆分并分配给GPU和CPU，这样双方就可以大致同时完成。结果，在空转和等待较慢的一侧完成时浪费的能量被最小化。在第二层中，绿色GPU根据利用率，以协调的方式动态调节GPU内核和内存的频率，以实现最大程度的节能，而性能仅会略有下降。同样，CPU的频率和电压也按比例缩放。我们使用CUDA框架在Nvidia GeForce GPU和AMD Phenom II CPU的真实物理测试台上实现Green GPU。实验结果表明，绿色GPU可以实现21.04％的平均节能量，并且优于几个精心设计的基准。
展开▼
